{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.04828", "kind": "paper", "url": "https://arxiv.org/abs/2608.04828"}], "authors": ["Jinyi Han", "Yuanjian Xu", "Ying Liao", "Xinyi Wang", "Zishang Jiang", "Zixiang Di", "Fanyang Lu", "Zhichao Hu", "Yanghua Xiao"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.04828", "source_url": "https://arxiv.org/abs/2608.04828"}, "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "Skill-Use evaluates skill use in agentic harnesses through 79 real skills and 177 executable tasks across nine domains, measuring trigger, compliance, and boundary adherence with a combined SU score."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.04828", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.04828", "title": "Skill-Use"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["East China Normal University", "Hong Kong University of Science and Technology", "Fudan University", "Tencent (China)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.04828", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.04828", "source_url": "https://openalex.org/W7196957808"}, "key": "claire-radar:2608.04828", "modality": null, "name": "Skill-Use", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_skill-use_dfe395c1", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "f13cca3f688aeba6b5d8b2e5376f45c1251c8c40d66065dfcc4b0d4d54bf63a5", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.04828"}, "publisher": null, "released": "2026-08-05", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.04828", "source_url": "https://arxiv.org/abs/2608.04828"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-04828", "source": "claire_radar", "source_benchmark_id": "2608.04828", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 1, "hfPaperUrl": "https://huggingface.co/papers/2608.04828", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "6a7c1ac3397cd3107e6e682fc0e118b50f3b5b22a71cde757279c5a932636cb0", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Skill-Use evaluates skill use in agentic harnesses through 79 real skills and 177 executable tasks across nine domains, measuring trigger, compliance, and boundary adherence with a combined SU score.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce Skill-Use, a benchmark that evaluates skill use under progressive disclosure, where an agent sees only a skill's name and short description and must retrieve the full procedure before following it."}, "familyId": "bmf_43888fe52bed", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_skill-use_dfe395c1", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.04828", "paper": "https://arxiv.org/abs/2608.04828", "pdf": "https://arxiv.org/pdf/2608.04828", "project": null, "report": "https://arxiv.org/abs/2608.04828"}, "metrics": [], "motivation": "Large language model (LLM) agents increasingly rely on skills, structured documents that specify when to act, which procedure to follow, and which tools are allowed.", "name": "Skill-Use", "oneLine": "Skill-Use evaluates skill use in agentic harnesses through 79 real skills and 177 executable tasks across nine domains, measuring trigger, compliance, and boundary adherence with a combined SU score.", "paperTitle": "Skill-Use: Can LLMs Actually Use Skills in Agentic Harnesses?", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.04828", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.12247537038455211, "value": 1}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 44}, "method": "attention-ranking-v13", "rank": null, "score": 44}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-05", "source": {"authors": ["Jinyi Han", "Yuanjian Xu", "Ying Liao", "Xinyi Wang", "Zishang Jiang", "Zixiang Di", "Fanyang Lu", "Zhichao Hu", "Yanghua Xiao"], "categories": ["cs.CL"], "id": "2608.04828", "title": "Skill-Use: Can LLMs Actually Use Skills in Agentic Harnesses?", "type": "arxiv", "url": "https://arxiv.org/abs/2608.04828"}, "sourceUpdatedAt": "2026-08-05T13:29:16Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Agent evaluations often focus on task success, not whether agents can autonomously identify and apply relevant skills. Skill-Use isolates skill retrieval and usage under progressive disclosure, showing harness-dependent capabilities."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
